基于二维时频谱图与改进YOLOv5的电能质量扰动识别  

PQD recognition using two-dimensional time-frequency spectrograms and an im⁃proved YOLOv5

作　　者：李欣 吕干云[1] 龚彧 毕睿华[1] 叶加星[3] 刘晓宏 于相宜 LI Xin;LYU Ganyun;GONG Yu;BI Ruihua;YE Jiaxing;LIU Xiaohong;YU Xiangyi(School of Electric Power Engineering,Nanjing Institute of Technology,Nanjing 211167,China;State Grid Yancheng Power Supply Company,Yancheng,Jiangsu 224000,China;Jiangsu Frontier Electric Technology Co.,Ltd.,Nanjing 211102,China)

机构地区：[1]南京工程学院电力工程学院,南京211167 [2]国网江苏省盐城供电分公司,江苏盐城224000 [3]江苏方天电力技术有限公司,南京211102

出　　处：《浙江电力》2024年第10期35-44,共10页Zhejiang Electric Power

基　　金：国家自然科学基金资助项目(51577086);江苏“六大人才高峰”资助(TD-XNY004)。

摘　　要：随着新型电力系统中新能源渗透率逐渐升高,电网结构复杂性增加,PQD(电能质量扰动)呈现多样化和复杂化的趋势。为实现电能质量扰动的精准识别,提出一种基于二维时频谱图与改进YOLOv5的电能质量扰动图像识别的方法。首先,利用S变换将PQD数据映射成二维时频谱图,通过图像来表征时间、频率和幅值的扰动细节特征;然后,搭建引入ASPP(空洞空间卷积池化金字塔)结构和注意力机制的YO-LOv5训练网络,扩大特征图的感受野以充分提取扰动图像特征,进而以图像识别方法实现PQD分类识别;最后,利用仿真数据进行扰动识别准确率和鲁棒性的验证。结果表明,该方法的识别准确率较高,且图像识别法的引入有助于PQD识别结果的可视化。As the penetration rate of renewable energy sources increases in new-type power systems,so too does the complexity of the grid structure,leading to more diverse and complex power quality disturbance(PQD).To accu⁃rately identify power quality,a method for PQD image recognition has been proposed,utilizing a two-dimensional time-frequency spectrograms and an improved YOLOv5.Initially,PQD data is projected onto a two-dimensional time-frequency spectrograms using the S-transform.This approach allows for detail-oriented representation of distur⁃bances in terms of time,frequency,and amplitude via imagery.Subsequently,a YOLOv5 training network is con⁃structed that integrates atrous spatial pyramid pooling(ASPP)structure and attention mechanisms.This design broadens the receptive field of the feature map,facilitating a comprehensive extraction of the disturbance image fea⁃tures,and enables PQD classification recognition through image detection methods.Finally,the accuracy and ro⁃bustness of the disturbance recognition are validated using simulation data.The results evidence that this method of⁃fers a high degree of recognition accuracy.Moreover,the integration of the image recognition method enhances the visual representation of the PQD recognition results.

关 键 词：电能质量扰动图像识别 时频谱图像 YOLOv5 空洞空间卷积池化金字塔 注意力机制 

分 类 号：TM711[电气工程—电力系统及自动化] TP391.41[自动化与计算机技术—计算机应用技术]